CS370: Introduction to Computer Vision

• Spring 2011; Monday and Wednesday, 10:35-11:50 • LGRC 310A (See map)

Instructor

Erik Learned-Miller
elm at cs.umass.edu
(413) 545-2993

Teaching Assistant

Manjunath Narayana
narayana at cs.umass.edu
(413) 545-0528
TA Office hours - Wednesday 12:00 PM to 2:00 PM in Edlab (LGRT 223)

Prerequisites

Reading Materials

Textbook: Algorithms and Applications, by Richard Szeliski: On-line copy available here

I do NOT recommend buying the textbook unless you want it for your own purposes. We will use it some in this course, but not a lot. You should be able to get by the the on-line version.

Resources

MATLAB Tutorial

Some pointers to get started with MATLAB on edlab machines

How can I access edlab machines remotely using my windows PC (Putty/Cygwin installation notes)

Interesting Links

Checker shadow illusion

Early color photographs by S. M. Prokudin-Gorsky

Flower Garden movie.

Non-lambertian reflectance functions

Explanation of hexagonal sampling efficiency

Problem Sets

Description

Schedule

Date	Lecture topic	New assignments	Assignments due	Reading
Jan. 19	Lecture Slides Introduction. What is Computer Vision?	Assignment 1: Read Lightness Perception and Lightness Illusions Come up with five questions relevant to the paper. These can be things you didn't understand after a careful reading of the paper, or questions which the paper raises. Turn in the answer written up as a .pdf file. You will be graded on the depth of your questions and how much thought you were judged to have put into them.	As. 1 due Jan. 26	Handout: Introduction to Computer Vision
Jan. 24	Introduction to using MATLAB for Computer Vision. MM's candy image used in lecture Matlab Session 1 Transcript from Lecture Matlab Session 2 Transcript from Lecture
Jan. 26	Formalizing the decision making process. Minimizing error. Maximizing utility. Review of basic probability theory. You will be responsible for all of the basic probability theory in this handout.	Assignment 2: Colorizing the Prokudin-Gorsky photo collection	As. 2 due Feb. 2	Probability handout (see lecture description).
Jan. 31	Probability review continued.
Feb. 2	SNOW DAY.
Feb. 7	Bayes rule. Minimizing probability of error. Utility. Introduction to supervised learning. Supervised learning for vision. Estimating distributions from data. Features of images.			Supervised learning handout.
Feb. 9	Classification of handwritten digits with simple features. Diary from lecture
Feb. 14	Estimating joint distributions of multiple variables. Leveraging independence for better estimation. More applications of Bayes' rule.
Feb. 16	More on independence. Alignment issues in computer vision.	Assignment 3: Single pixel classification of digits. Download digits here.	Due, Monday, February 21 by end of day.
Feb. 22	The three parts of alignment: Similarity and difference functions, sets of transformations, and optimization methods
Feb. 23	Alignment continued and how to transform an image.	Assignment 4: Multiple pixel classification of digits. Download digits here.	Due, Wednesday March 2 end of day.
Feb. 28	Transforming images in matlab. Avoiding "holes" in images by inverse transforming. Minimizing difference function over transformations. Three matlab files from class: rotate1.m rotate2.m demo.m			Assignment 3 solution: likFromTraining.m Assignment 3 solution: BayesRule.m Assignment 3 solution: classifyTestData.m
Mar. 2
Mar. 7	Midterm review.			Assignment4 solution: likFromTraining_multi.m Assignment4 solution: BayesRule_multi.m Assignment4 solution: classifyTestData_multi.m
Mar. 9	************************** IN CLASS MIDTERM **********************
Mar. 14	No Class - Spring break.
Mar. 16	No Class - Spring break.
Mar. 21	The role of optics and photogrammetry in computer vision. Electromagnetic spectrum. Visible light. Composition of visible light.
Mar. 23	Point light sources. Steradians. Solid angle. Watts of a light source. Inverse square law. Reflection, scattering.			Light sources and camera models handout.
Mar. 28
Mar. 30	Background substraction			Background modeling (subtraction) introduction
Apr 4	Background substraction continued.	Assignment 5: Cameras and light.	Due, Monday April 18 end of day.
Apr. 6	Background on convolution, delta functions, using convolution to help in density estimation.			Convolution (wikipedia link)
Apr. 11	Overview of Face recognition. Detection, alignment, recognition.
Apr. 18	No class. HOLIDAY
Apr. 20	More on distribution fields. Finish background subtraction.	Assignment 6: Background subtraction train_data.mat test_data.mat
Apr. 25	Slides on edges
Apr. 27	Slides on SIFT
May 2	LAST DAY OF CLASS. Review for FINAL.			Assignment5 solution: Pinhole camera problem
May 9 1:30 PM	*FINAL EXAM *: 1:30pm, Computer Science building room 140			Exam 1 review handout Final Exam review handout